Evaluating Human Trajectory Prediction with Metamorphic Testing
Not on the map. Why?
Abstract (arXiv)
The prediction of human trajectories is important for planning in autonomous systems that act in the real world, e.g. automated driving or mobile robots. Human trajectory prediction is a noisy process, and no prediction does precisely match any future trajectory. It is therefore approached as a stochastic problem, where the goal is to minimise the error between the true and the predicted trajectory. In this work, we explore the application of metamorphic testing for human trajectory prediction. Metamorphic testing is designed to handle unclear or missing test oracles. It is well-designed for human trajectory prediction, where there is no clear criterion of correct or incorrect human behaviour. Metamorphic relations rely on transformations over source test cases and exploit invariants. A setting well-designed for human trajectory prediction where there are many symmetries of expected human behaviour under variations of the input, e.g. mirroring and rescaling of the input data. We discuss how metamorphic testing can be applied to stochastic human trajectory prediction and introduce the Wasserstein Violation Criterion to statistically assess whether a follow-up test case violates a label-preserving metamorphic relation.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 26 Jul 2024.
Builds on
18 of 42 references.
References · 18
- 2018Computational Optimal Transportcited by 765
- 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
- 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
- 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
- 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 213
- 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
- 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 89
- 2020Metamorphic Testing: A New Approach for Generating Next Test Casescited by 71
- 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
- 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 48
- 2022Non-Probability Sampling Network for Stochastic Human Trajectory Predictioncited by 46
- 2019Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervisioncited by 27
6 more
- 2022Targeted Adversarial Attacks against Neural Network Trajectory Predictorscited by 11
- 2023Evaluating Pedestrian Trajectory Prediction Methods with Respect to Autonomous Drivingcited by 11
- 2020A Declarative Metamorphic Testing Framework for Autonomous Drivingcited by 10
- 2023TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Modelscited by 8
- 2019Adaptive Metamorphic Testing with Contextual Banditscited by 7
- 2020SimAug: Learning Robust Representations from Simulation for Trajectory Predictioncited by 6
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.